Back to EveryPatent.com
United States Patent | 6,055,499 |
Chengalvarayan ,   et al. | April 25, 2000 |
A class of features related to voicing parameters that indicate whether the vocal chords are vibrating. Features describing voicing characteristics of speech signals are integrated with an existing 38-dimensional feature vector consisting of first and second order time derivatives of the frame energy and of the cepstral coefficients with their first and second derivatives. Hidden Markov Model (HMM)-based connected digit recognition experiments comparing the traditional and extended feature sets show that voicing features and spectral information are complementary and that improved speech recognition performance is obtained by combining the two sources of information.
Inventors: | Chengalvarayan; Rathinavelu (Lisle, IL); Thomson; David Lynn (Lisle, IL) |
Assignee: | Lucent Technologies Inc. (Murray Hill, NJ) |
Appl. No.: | 071214 |
Filed: | May 1, 1998 |
Current U.S. Class: | 704/250; 704/207 |
Intern'l Class: | G10L 015/02 |
Field of Search: | 704/250,205,206,207,208,217,216,256,255 |
5611019 | Mar., 1997 | Nakatoh et al. | 704/233. |
5729694 | Mar., 1998 | Holzrichter et al. | 704/208. |
J. Schoentgen et al., Predictable and Random Components of Jitter:, Speech Communication, No. 21, 1997, pp. 255-272. B-H. Juang et al., Minimum Classification Error Rate Methods for Speech Recognition, IEEE Transactions on Speech and Audio Processing, vol. 5, No. 3, May, 1997, pp. 257-265. E. L. Bocchieri et al., Discriminative Feature Selection for Speech Recognition, Computer Speech and Language, (1993) 7, pp. 229-246. D. P. Prezas et al., Fast and Accurate Pitch Detection Using Pattern Recognition and Adaptive Time-Domain Analysis, ICASSP 86, Tokyo, pp. 109-112. W. Chou et al., Signal Conditioned Minimum Error Rate Training, Eurospeech 95 pp. 495-498. B. H. Juang et al., On the Use of Bandpass Liftering in Speech Recognition, ICASSP 86, Tokyo, pp. 765-768. B. S. Atal et al., A Pattern Recognition Approach to Voiced-Unvoiced-Silence Classification with Applications to Speech Recognition, IEEE Transactions On Acoustics, Speech, And Signal Processing, vol. ASSP-24, No. 3, Jun., 1976, pp. 201-212. |
TABLE 2 ______________________________________ Feature Vector ML Training MSE Training Size and Type Wd Err St. Err Wd. Err St. Brr ______________________________________ 38 DDCEP.sup.+ 3.31% 16.61% 2.14% 10.18% 44 DDCEP* 3.07% 15.78% 1.28% 6.42% ______________________________________